fragmentation_analysis

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the transparency burden. It marks itself as `[READ]`, describes ranking/analysis rather than mutation, and states that each recommendation cites its numbers. It also warns that live fetching occurs when `tables` is omitted, which is useful context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is 4 sentences plus a compact args list. It front-loads the core purpose, then explains modes, then parameters. No redundant or vague text.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no output schema, it notes that recommendations cite their numbers, giving a hint about the return. It covers all parameters and usage modes. However, it doesn't detail the exact output structure or criteria for ranking beyond 'reclaimable data_free', so a 4 is warranted.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description compensates fully: `tables` (injected rows vs live pull), `limit` (how many tables when not injected, default 50), and `target` (config name, omit for default). Every parameter is explained with behavior and default.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with '[READ] Rank tables by reclaimable data_free into OPTIMIZE TABLE candidates,' which names a specific verb ('rank'), a resource ('tables'), and a purpose (identify OPTIMIZE TABLE candidates). It distinguishes itself from siblings like `table_fragmentation` by referencing it as a data source and `optimize_table` by stopping at candidate ranking.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly describes two invocation modes: pass `tables` (as from `table_fragmentation`) for offline analysis, or omit to pull the worst-fragmented tables live. This tells an agent when each mode is appropriate, though it doesn't explicitly list exclusions or alternatives beyond the reference to `table_fragmentation`.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.